Summary
Apple describes four Audio Intelligence features for Apple Watch Series 12 and Apple Watch Ultra 4: sound alerts, automatic song recognition, Live Rewind and Siri Recap. Live Rewind and Siri Recap are planned for beta later this year, starting in English.
Apple’s support documentation describes four Audio Intelligence features for Apple Watch Series 12 and Apple Watch Ultra 4: Sound Recognition, automatic Music Recognition with Shazam, Live Rewind and Siri Recap. The first two detect sounds or identify music; Live Rewind and Siri Recap are planned for beta later this year, starting in English.
Contents
What the features do
Sound Recognition can alert the wearer to sounds such as sirens, alarms and doorbells, including when an iPhone is not nearby. Apple highlights its potential usefulness for people who are deaf or hard of hearing. Music Recognition automatically identifies background music and puts the song title and artist in the watch’s Smart Stack.
Live Rewind is designed for a moment when someone misses a short part of a conversation: double-pressing the Digital Crown displays a text snippet of the previous 15 seconds of speech. Siri Recap takes a different approach. When enabled, it creates high-level summaries of conversations that can later help jog the wearer’s memory. Apple says these are summaries rather than transcripts, and that they do not identify or label speakers.
These features have different triggers. Live Rewind activates with a deliberate double-press, while Siri Recap runs only when the wearer chooses to enable it, either manually or on a schedule. Apple says Live Rewind also produces a chime and a visible screen animation when activated.
How audio is processed
Apple says the features use the S11 chip’s Secure Exclave, a hardware-isolated environment for processing sensor data. Its stated privacy design does not create or store audio recordings. For music recognition, the watch generates an acoustic signature and sends that compact representation—not raw audio—to Shazam for identification.
Sound Recognition and Live Rewind are processed on the Watch and paired iPhone. Siri Recap uses a more involved route: the watch sends encrypted audio to the iPhone’s Secure Exclave, where it is transcribed and condensed. The condensed text is then sent to Apple’s Private Cloud Compute to generate a summary. Apple says the summaries and any saved Live Rewind snippets sync through iCloud with end-to-end encryption.
The distinction matters because a feature can process conversation audio without producing a full transcript for the wearer. Siri Recap’s output is intended to be brief and high-level; Live Rewind provides a short text extract only after the wearer activates it.
Controls and availability
Sound Recognition and automatic Music Recognition require an Apple Watch Series 12 or Apple Watch Ultra 4 paired with an iPhone 11 or later, or iPhone SE (2nd generation or later), running iOS 27. Live Rewind and Siri Recap require one of the same watch models, a supported iPhone listed by Apple, and Apple Intelligence and Siri AI (Beta).
Apple says Live Rewind and Siri Recap will be available in beta later this year and will initially support English. They are unavailable to users under 13; for users under 18 on a Child Account, a parent or guardian must enable access. Apple also cautions that generated summaries and text snippets can be incomplete or inaccurate, so important details may need confirmation.